{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ASEYMYS4YTRSEQ6TIFJV7KBNGE","short_pith_number":"pith:ASEYMYS4","schema_version":"1.0","canonical_sha256":"048986625cc4e32243d341535fa82d3107718d04edbdbac6ad441f7cbde69f2b","source":{"kind":"arxiv","id":"1807.11714","version":2},"attestation_state":"computed","paper":{"title":"Gender Bias in Neural Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anupam Datta, Fangjing Wu, Kaiji Lu, Piotr Mardziel, Preetam Amancharla","submitted_at":"2018-07-31T09:27:27Z","abstract_excerpt":"We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with state-of-the-art neural coreference resolution and textbook RNN-based language models trained on benchmark datasets finds significant gender bias in how models view occupations. We then mitigate bias with CDA: a generic methodology for corpus augmentation via causal interventions that breaks associations between gendered and gender-neutral words. We empirically show t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1807.11714","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-31T09:27:27Z","cross_cats_sorted":[],"title_canon_sha256":"a86a7c281a044c1f72bafb3b4dd3c7a673a347ccfde90944bb6aec5b866d9895","abstract_canon_sha256":"808913e57fd4e50f31239400af61e08232dd492f00cda808f9ca259d4a78a1e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:38.134779Z","signature_b64":"+wwZ8ouGxERo39v0KYjH7iSLvoLpwArnDn8ylYuY1K4faTF+nX35+CFV10HLQN+9H5CkaxkI6Ff5AZnCDqKdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"048986625cc4e32243d341535fa82d3107718d04edbdbac6ad441f7cbde69f2b","last_reissued_at":"2026-05-17T23:44:38.134254Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:38.134254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gender Bias in Neural Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anupam Datta, Fangjing Wu, Kaiji Lu, Piotr Mardziel, Preetam Amancharla","submitted_at":"2018-07-31T09:27:27Z","abstract_excerpt":"We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with state-of-the-art neural coreference resolution and textbook RNN-based language models trained on benchmark datasets finds significant gender bias in how models view occupations. We then mitigate bias with CDA: a generic methodology for corpus augmentation via causal interventions that breaks associations between gendered and gender-neutral words. We empirically show t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11714","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.11714","created_at":"2026-05-17T23:44:38.134331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.11714v2","created_at":"2026-05-17T23:44:38.134331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11714","created_at":"2026-05-17T23:44:38.134331+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASEYMYS4YTRS","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASEYMYS4YTRSEQ6T","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASEYMYS4","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2310.10865","citing_title":"Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"1905.00537","citing_title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","ref_index":121,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE","json":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE.json","graph_json":"https://pith.science/api/pith-number/ASEYMYS4YTRSEQ6TIFJV7KBNGE/graph.json","events_json":"https://pith.science/api/pith-number/ASEYMYS4YTRSEQ6TIFJV7KBNGE/events.json","paper":"https://pith.science/paper/ASEYMYS4"},"agent_actions":{"view_html":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE","download_json":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE.json","view_paper":"https://pith.science/paper/ASEYMYS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.11714&json=true","fetch_graph":"https://pith.science/api/pith-number/ASEYMYS4YTRSEQ6TIFJV7KBNGE/graph.json","fetch_events":"https://pith.science/api/pith-number/ASEYMYS4YTRSEQ6TIFJV7KBNGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE/action/storage_attestation","attest_author":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE/action/author_attestation","sign_citation":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE/action/citation_signature","submit_replication":"https://pith.science/pith/ASEYMYS4YTRSEQ6TIFJV7KBNGE/action/replication_record"}},"created_at":"2026-05-17T23:44:38.134331+00:00","updated_at":"2026-05-17T23:44:38.134331+00:00"}